A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments
Urban population distribution maps are vital elements for monitoring the Sustainable Development Goals, appropriately allocating resources such as vaccination campaigns, and facilitating evidence-based decision making. Typically, population distribution maps are derived from census data from the reg...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-11-01
|
Series: | International Journal of Applied Earth Observations and Geoinformation |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843222002011 |
_version_ | 1797990078680662016 |
---|---|
author | Stefanos Georganos Sebastian Hafner Monika Kuffer Catherine Linard Yifang Ban |
author_facet | Stefanos Georganos Sebastian Hafner Monika Kuffer Catherine Linard Yifang Ban |
author_sort | Stefanos Georganos |
collection | DOAJ |
description | Urban population distribution maps are vital elements for monitoring the Sustainable Development Goals, appropriately allocating resources such as vaccination campaigns, and facilitating evidence-based decision making. Typically, population distribution maps are derived from census data from the region of interest. Nevertheless, in several low- and middle-income countries, census information may be unreliable, outdated or unsuitable for spatial analysis at the intra-urban level, which poses severe limitations in the development of urban population maps of adequate quality. To address these shortcomings, we deploy a novel framework utilizing multisource Earth Observation (EO) information such as Sentinel-2 and very-high-resolution Pleiades imagery, openly available building footprint datasets, and deep learning (DL) architectures, providing end-to-end solutions to the production of high quality intra-urban population distribution maps in data scarce contexts. Using several case studies in Sub-Saharan Africa, namely Dakar (Senegal), Nairobi (Kenya) and Dar es Salaam (Tanzania), our results emphasize that the combination of DL and EO data is very potent and can successfully capture relationships between the retrieved image features and population counts at fine spatial resolutions (100 meter). Moreover, for the first time, we used state-of-the-art domain adaptation methods to predict population distributions in Dar es Salaam and Nairobi (R2 = 0.39, 0.60) that did not require national census or survey data from Kenya or Tanzania, but only a sample of training locations from Dakar. The DL architecture is based on a modified ResNet-18 model with dual-streams to analyze multi-modal data. Our findings have strong implications for the development of a new generation of urban population products that are an output of end-to-end solutions, can be updated frequently and rely completely on open data. |
first_indexed | 2024-04-11T08:29:39Z |
format | Article |
id | doaj.art-0c83f4d004c449aa89e0306d12b2d163 |
institution | Directory Open Access Journal |
issn | 1569-8432 |
language | English |
last_indexed | 2024-04-11T08:29:39Z |
publishDate | 2022-11-01 |
publisher | Elsevier |
record_format | Article |
series | International Journal of Applied Earth Observations and Geoinformation |
spelling | doaj.art-0c83f4d004c449aa89e0306d12b2d1632022-12-22T04:34:33ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322022-11-01114103013A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environmentsStefanos Georganos0Sebastian Hafner1Monika Kuffer2Catherine Linard3Yifang Ban4Division of Geoinformatics, KTH Royal Institute of Technology, Stockholm 10044, Sweden; Corresponding author.Division of Geoinformatics, KTH Royal Institute of Technology, Stockholm 10044, SwedenFaculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7514 AE Enschede, The NetherlandsInstitute of Life, Earth and Environment, Université de Namur, Namur, Belgium; Department of Geography, Université de Namur, Namur, BelgiumDivision of Geoinformatics, KTH Royal Institute of Technology, Stockholm 10044, SwedenUrban population distribution maps are vital elements for monitoring the Sustainable Development Goals, appropriately allocating resources such as vaccination campaigns, and facilitating evidence-based decision making. Typically, population distribution maps are derived from census data from the region of interest. Nevertheless, in several low- and middle-income countries, census information may be unreliable, outdated or unsuitable for spatial analysis at the intra-urban level, which poses severe limitations in the development of urban population maps of adequate quality. To address these shortcomings, we deploy a novel framework utilizing multisource Earth Observation (EO) information such as Sentinel-2 and very-high-resolution Pleiades imagery, openly available building footprint datasets, and deep learning (DL) architectures, providing end-to-end solutions to the production of high quality intra-urban population distribution maps in data scarce contexts. Using several case studies in Sub-Saharan Africa, namely Dakar (Senegal), Nairobi (Kenya) and Dar es Salaam (Tanzania), our results emphasize that the combination of DL and EO data is very potent and can successfully capture relationships between the retrieved image features and population counts at fine spatial resolutions (100 meter). Moreover, for the first time, we used state-of-the-art domain adaptation methods to predict population distributions in Dar es Salaam and Nairobi (R2 = 0.39, 0.60) that did not require national census or survey data from Kenya or Tanzania, but only a sample of training locations from Dakar. The DL architecture is based on a modified ResNet-18 model with dual-streams to analyze multi-modal data. Our findings have strong implications for the development of a new generation of urban population products that are an output of end-to-end solutions, can be updated frequently and rely completely on open data.http://www.sciencedirect.com/science/article/pii/S1569843222002011Population mappingGlobal SouthEarth ObservationDeep learningUrban sustainabilityDomain adaptation |
spellingShingle | Stefanos Georganos Sebastian Hafner Monika Kuffer Catherine Linard Yifang Ban A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments International Journal of Applied Earth Observations and Geoinformation Population mapping Global South Earth Observation Deep learning Urban sustainability Domain adaptation |
title | A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments |
title_full | A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments |
title_fullStr | A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments |
title_full_unstemmed | A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments |
title_short | A census from heaven: Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments |
title_sort | census from heaven unraveling the potential of deep learning and earth observation for intra urban population mapping in data scarce environments |
topic | Population mapping Global South Earth Observation Deep learning Urban sustainability Domain adaptation |
url | http://www.sciencedirect.com/science/article/pii/S1569843222002011 |
work_keys_str_mv | AT stefanosgeorganos acensusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT sebastianhafner acensusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT monikakuffer acensusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT catherinelinard acensusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT yifangban acensusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT stefanosgeorganos censusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT sebastianhafner censusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT monikakuffer censusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT catherinelinard censusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments AT yifangban censusfromheavenunravelingthepotentialofdeeplearningandearthobservationforintraurbanpopulationmappingindatascarceenvironments |